ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k1_task7_organization

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4078
• Qwk: 0.6747
• Mse: 0.4078
• Rmse: 0.6386

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.4	2	2.4831	-0.0449	2.4831	1.5758
No log	0.8	4	1.2421	0.0997	1.2421	1.1145
No log	1.2	6	0.7761	0.1372	0.7761	0.8810
No log	1.6	8	0.9516	0.0327	0.9516	0.9755
No log	2.0	10	1.0156	0.1709	1.0156	1.0078
No log	2.4	12	1.0486	0.2903	1.0486	1.0240
No log	2.8	14	0.8951	0.2094	0.8951	0.9461
No log	3.2	16	0.7865	0.0608	0.7865	0.8868
No log	3.6	18	0.7732	0.1232	0.7732	0.8793
No log	4.0	20	0.7328	0.1646	0.7328	0.8560
No log	4.4	22	0.6772	0.1498	0.6772	0.8229
No log	4.8	24	0.6729	0.4243	0.6729	0.8203
No log	5.2	26	0.6281	0.4414	0.6281	0.7925
No log	5.6	28	0.5447	0.4314	0.5447	0.7380
No log	6.0	30	0.5724	0.5301	0.5724	0.7566
No log	6.4	32	0.7240	0.3783	0.7240	0.8509
No log	6.8	34	0.6116	0.4652	0.6116	0.7820
No log	7.2	36	0.4918	0.6039	0.4918	0.7013
No log	7.6	38	0.4871	0.6087	0.4871	0.6979
No log	8.0	40	0.5781	0.4892	0.5781	0.7603
No log	8.4	42	0.6469	0.4377	0.6469	0.8043
No log	8.8	44	0.5355	0.5538	0.5355	0.7318
No log	9.2	46	0.5505	0.6519	0.5505	0.7420
No log	9.6	48	0.5989	0.6439	0.5989	0.7739
No log	10.0	50	0.4921	0.6730	0.4921	0.7015
No log	10.4	52	0.6389	0.4881	0.6389	0.7993
No log	10.8	54	0.5715	0.5124	0.5715	0.7560
No log	11.2	56	0.4566	0.6676	0.4566	0.6757
No log	11.6	58	0.4451	0.6932	0.4451	0.6671
No log	12.0	60	0.4772	0.6389	0.4772	0.6908
No log	12.4	62	0.4194	0.7119	0.4194	0.6476
No log	12.8	64	0.4590	0.6080	0.4590	0.6775
No log	13.2	66	0.4159	0.6334	0.4159	0.6449
No log	13.6	68	0.4343	0.6716	0.4343	0.6590
No log	14.0	70	0.7542	0.3961	0.7542	0.8685
No log	14.4	72	0.8285	0.3961	0.8285	0.9102
No log	14.8	74	0.5590	0.5489	0.5590	0.7477
No log	15.2	76	0.4470	0.6115	0.4470	0.6686
No log	15.6	78	0.6693	0.6021	0.6693	0.8181
No log	16.0	80	0.5836	0.5463	0.5836	0.7639
No log	16.4	82	0.4361	0.7004	0.4361	0.6604
No log	16.8	84	0.5784	0.5887	0.5784	0.7605
No log	17.2	86	0.5749	0.5887	0.5749	0.7582
No log	17.6	88	0.4430	0.6855	0.4430	0.6655
No log	18.0	90	0.5173	0.5695	0.5173	0.7192
No log	18.4	92	0.6278	0.5677	0.6278	0.7924
No log	18.8	94	0.5098	0.5748	0.5098	0.7140
No log	19.2	96	0.4249	0.6575	0.4249	0.6518
No log	19.6	98	0.4996	0.5429	0.4996	0.7068
No log	20.0	100	0.4832	0.5779	0.4832	0.6951
No log	20.4	102	0.4276	0.6467	0.4276	0.6539
No log	20.8	104	0.4873	0.6267	0.4873	0.6981
No log	21.2	106	0.4672	0.6356	0.4672	0.6835
No log	21.6	108	0.4253	0.6577	0.4253	0.6521
No log	22.0	110	0.4193	0.6870	0.4193	0.6475
No log	22.4	112	0.4126	0.6870	0.4126	0.6424
No log	22.8	114	0.4060	0.6957	0.4060	0.6372
No log	23.2	116	0.4115	0.6705	0.4115	0.6415
No log	23.6	118	0.4242	0.6793	0.4242	0.6513
No log	24.0	120	0.4217	0.6884	0.4217	0.6493
No log	24.4	122	0.4123	0.6884	0.4123	0.6421
No log	24.8	124	0.4169	0.6701	0.4169	0.6457
No log	25.2	126	0.3839	0.7032	0.3839	0.6196
No log	25.6	128	0.3950	0.6572	0.3950	0.6285
No log	26.0	130	0.4068	0.6900	0.4068	0.6378
No log	26.4	132	0.4124	0.6805	0.4124	0.6422
No log	26.8	134	0.4075	0.6496	0.4075	0.6384
No log	27.2	136	0.4115	0.6852	0.4115	0.6415
No log	27.6	138	0.4076	0.6161	0.4076	0.6384
No log	28.0	140	0.4019	0.6092	0.4019	0.6339
No log	28.4	142	0.4192	0.6601	0.4192	0.6475
No log	28.8	144	0.4584	0.6537	0.4584	0.6771
No log	29.2	146	0.4481	0.6342	0.4481	0.6694
No log	29.6	148	0.4046	0.6289	0.4046	0.6361
No log	30.0	150	0.4170	0.6472	0.4170	0.6458
No log	30.4	152	0.4199	0.6662	0.4199	0.6480
No log	30.8	154	0.4241	0.6337	0.4241	0.6512
No log	31.2	156	0.4369	0.6526	0.4369	0.6610
No log	31.6	158	0.4396	0.6526	0.4396	0.6630
No log	32.0	160	0.4225	0.6377	0.4225	0.6500
No log	32.4	162	0.4419	0.6228	0.4419	0.6647
No log	32.8	164	0.4786	0.5668	0.4786	0.6918
No log	33.2	166	0.4783	0.5701	0.4783	0.6916
No log	33.6	168	0.4403	0.6739	0.4403	0.6636
No log	34.0	170	0.4452	0.6491	0.4452	0.6672
No log	34.4	172	0.4400	0.6491	0.4400	0.6633
No log	34.8	174	0.4375	0.6667	0.4375	0.6614
No log	35.2	176	0.4714	0.6693	0.4714	0.6866
No log	35.6	178	0.4699	0.6944	0.4699	0.6855
No log	36.0	180	0.4550	0.6656	0.4550	0.6746
No log	36.4	182	0.4608	0.6574	0.4608	0.6788
No log	36.8	184	0.4634	0.6100	0.4634	0.6807
No log	37.2	186	0.4760	0.6259	0.4760	0.6899
No log	37.6	188	0.4606	0.6066	0.4606	0.6786
No log	38.0	190	0.4457	0.6818	0.4457	0.6676
No log	38.4	192	0.4602	0.5845	0.4602	0.6784
No log	38.8	194	0.4530	0.5816	0.4530	0.6730
No log	39.2	196	0.4429	0.6747	0.4429	0.6655
No log	39.6	198	0.4429	0.6747	0.4429	0.6655
No log	40.0	200	0.4429	0.5816	0.4429	0.6655
No log	40.4	202	0.4386	0.6655	0.4386	0.6622
No log	40.8	204	0.4625	0.5212	0.4625	0.6801
No log	41.2	206	0.4678	0.5283	0.4678	0.6839
No log	41.6	208	0.4375	0.5265	0.4375	0.6614
No log	42.0	210	0.4334	0.6505	0.4334	0.6583
No log	42.4	212	0.4565	0.6505	0.4565	0.6756
No log	42.8	214	0.4456	0.6505	0.4456	0.6675
No log	43.2	216	0.4197	0.6843	0.4197	0.6479
No log	43.6	218	0.4406	0.6223	0.4406	0.6638
No log	44.0	220	0.4791	0.5794	0.4791	0.6921
No log	44.4	222	0.4867	0.5794	0.4867	0.6976
No log	44.8	224	0.4550	0.5512	0.4550	0.6745
No log	45.2	226	0.4260	0.6464	0.4260	0.6527
No log	45.6	228	0.4490	0.6228	0.4490	0.6701
No log	46.0	230	0.4906	0.6681	0.4906	0.7004
No log	46.4	232	0.4778	0.6406	0.4778	0.6912
No log	46.8	234	0.4432	0.6408	0.4432	0.6657
No log	47.2	236	0.4286	0.6125	0.4286	0.6547
No log	47.6	238	0.4285	0.6330	0.4285	0.6546
No log	48.0	240	0.4341	0.6530	0.4341	0.6589
No log	48.4	242	0.4475	0.6518	0.4475	0.6689
No log	48.8	244	0.4306	0.6530	0.4306	0.6562
No log	49.2	246	0.4268	0.6351	0.4268	0.6533
No log	49.6	248	0.4332	0.5890	0.4332	0.6582
No log	50.0	250	0.4363	0.5319	0.4363	0.6605
No log	50.4	252	0.4274	0.6053	0.4274	0.6537
No log	50.8	254	0.4229	0.6344	0.4229	0.6503
No log	51.2	256	0.4296	0.6129	0.4296	0.6555
No log	51.6	258	0.4273	0.6129	0.4273	0.6537
No log	52.0	260	0.4295	0.6129	0.4295	0.6554
No log	52.4	262	0.4310	0.6129	0.4310	0.6565
No log	52.8	264	0.4315	0.6554	0.4315	0.6569
No log	53.2	266	0.4329	0.6383	0.4329	0.6579
No log	53.6	268	0.4340	0.6301	0.4340	0.6588
No log	54.0	270	0.4375	0.6301	0.4375	0.6614
No log	54.4	272	0.4407	0.6301	0.4407	0.6639
No log	54.8	274	0.4424	0.6301	0.4424	0.6651
No log	55.2	276	0.4376	0.6383	0.4376	0.6615
No log	55.6	278	0.4406	0.6241	0.4406	0.6638
No log	56.0	280	0.4356	0.6024	0.4356	0.6600
No log	56.4	282	0.4341	0.6039	0.4341	0.6588
No log	56.8	284	0.4351	0.6024	0.4352	0.6597
No log	57.2	286	0.4468	0.6228	0.4468	0.6684
No log	57.6	288	0.4433	0.6228	0.4433	0.6658
No log	58.0	290	0.4352	0.6317	0.4352	0.6597
No log	58.4	292	0.4287	0.6111	0.4287	0.6547
No log	58.8	294	0.4243	0.5899	0.4243	0.6514
No log	59.2	296	0.4247	0.6053	0.4247	0.6517
No log	59.6	298	0.4320	0.5248	0.4320	0.6573
No log	60.0	300	0.4255	0.6269	0.4255	0.6523
No log	60.4	302	0.4198	0.6269	0.4198	0.6479
No log	60.8	304	0.4132	0.6269	0.4132	0.6428
No log	61.2	306	0.4086	0.6269	0.4086	0.6392
No log	61.6	308	0.4066	0.6357	0.4066	0.6376
No log	62.0	310	0.4051	0.6269	0.4051	0.6365
No log	62.4	312	0.3995	0.6555	0.3995	0.6321
No log	62.8	314	0.4025	0.6935	0.4025	0.6344
No log	63.2	316	0.4018	0.6747	0.4018	0.6339
No log	63.6	318	0.4004	0.6555	0.4004	0.6327
No log	64.0	320	0.3988	0.6555	0.3988	0.6315
No log	64.4	322	0.4033	0.6269	0.4033	0.6351
No log	64.8	324	0.3985	0.6464	0.3985	0.6313
No log	65.2	326	0.3983	0.6919	0.3983	0.6311
No log	65.6	328	0.4081	0.7053	0.4081	0.6388
No log	66.0	330	0.4080	0.7053	0.4080	0.6387
No log	66.4	332	0.4014	0.6650	0.4014	0.6335
No log	66.8	334	0.3980	0.6464	0.3980	0.6309
No log	67.2	336	0.3967	0.6464	0.3967	0.6298
No log	67.6	338	0.3998	0.6464	0.3998	0.6323
No log	68.0	340	0.3988	0.6556	0.3988	0.6315
No log	68.4	342	0.3991	0.6555	0.3991	0.6318
No log	68.8	344	0.4021	0.6542	0.4021	0.6341
No log	69.2	346	0.4071	0.6632	0.4071	0.6380
No log	69.6	348	0.4053	0.6632	0.4053	0.6366
No log	70.0	350	0.3963	0.6747	0.3963	0.6295
No log	70.4	352	0.4007	0.6667	0.4007	0.6330
No log	70.8	354	0.4234	0.6034	0.4234	0.6507
No log	71.2	356	0.4467	0.5636	0.4467	0.6683
No log	71.6	358	0.4443	0.5498	0.4443	0.6666
No log	72.0	360	0.4237	0.5554	0.4237	0.6509
No log	72.4	362	0.4067	0.6554	0.4067	0.6377
No log	72.8	364	0.4085	0.6739	0.4085	0.6392
No log	73.2	366	0.4164	0.6431	0.4164	0.6453
No log	73.6	368	0.4198	0.6530	0.4198	0.6479
No log	74.0	370	0.4229	0.6330	0.4229	0.6503
No log	74.4	372	0.4228	0.6125	0.4228	0.6502
No log	74.8	374	0.4205	0.6555	0.4205	0.6484
No log	75.2	376	0.4215	0.6555	0.4215	0.6492
No log	75.6	378	0.4219	0.6555	0.4219	0.6495
No log	76.0	380	0.4219	0.6555	0.4219	0.6496
No log	76.4	382	0.4229	0.6555	0.4229	0.6503
No log	76.8	384	0.4283	0.6053	0.4283	0.6545
No log	77.2	386	0.4344	0.5846	0.4344	0.6591
No log	77.6	388	0.4340	0.5846	0.4340	0.6588
No log	78.0	390	0.4306	0.6554	0.4306	0.6562
No log	78.4	392	0.4338	0.6739	0.4338	0.6586
No log	78.8	394	0.4396	0.6634	0.4396	0.6630
No log	79.2	396	0.4423	0.6702	0.4423	0.6650
No log	79.6	398	0.4386	0.6880	0.4386	0.6623
No log	80.0	400	0.4280	0.6807	0.4280	0.6542
No log	80.4	402	0.4169	0.6639	0.4169	0.6457
No log	80.8	404	0.4098	0.6747	0.4098	0.6402
No log	81.2	406	0.4068	0.6747	0.4068	0.6378
No log	81.6	408	0.4073	0.6555	0.4073	0.6382
No log	82.0	410	0.4114	0.6377	0.4114	0.6414
No log	82.4	412	0.4120	0.6577	0.4120	0.6419
No log	82.8	414	0.4093	0.6464	0.4093	0.6397
No log	83.2	416	0.4075	0.6554	0.4075	0.6383
No log	83.6	418	0.4122	0.6730	0.4122	0.6420
No log	84.0	420	0.4173	0.6634	0.4173	0.6460
No log	84.4	422	0.4178	0.6634	0.4178	0.6463
No log	84.8	424	0.4151	0.6634	0.4151	0.6443
No log	85.2	426	0.4137	0.6730	0.4137	0.6432
No log	85.6	428	0.4118	0.6730	0.4118	0.6417
No log	86.0	430	0.4095	0.6739	0.4095	0.6399
No log	86.4	432	0.4084	0.6554	0.4084	0.6391
No log	86.8	434	0.4089	0.6555	0.4089	0.6394
No log	87.2	436	0.4083	0.6555	0.4083	0.6390
No log	87.6	438	0.4071	0.6555	0.4071	0.6381
No log	88.0	440	0.4063	0.6555	0.4063	0.6374
No log	88.4	442	0.4060	0.6739	0.4060	0.6372
No log	88.8	444	0.4059	0.6739	0.4059	0.6371
No log	89.2	446	0.4048	0.6747	0.4048	0.6362
No log	89.6	448	0.4037	0.6747	0.4037	0.6353
No log	90.0	450	0.4032	0.6747	0.4032	0.6350
No log	90.4	452	0.4040	0.6747	0.4040	0.6356
No log	90.8	454	0.4044	0.6747	0.4044	0.6359
No log	91.2	456	0.4044	0.6747	0.4044	0.6359
No log	91.6	458	0.4050	0.6747	0.4050	0.6364
No log	92.0	460	0.4063	0.6747	0.4063	0.6374
No log	92.4	462	0.4064	0.6747	0.4064	0.6375
No log	92.8	464	0.4056	0.6747	0.4056	0.6368
No log	93.2	466	0.4052	0.6747	0.4052	0.6365
No log	93.6	468	0.4051	0.6747	0.4051	0.6365
No log	94.0	470	0.4052	0.6747	0.4052	0.6365
No log	94.4	472	0.4049	0.6747	0.4049	0.6363
No log	94.8	474	0.4053	0.6747	0.4053	0.6367
No log	95.2	476	0.4058	0.6747	0.4058	0.6370
No log	95.6	478	0.4060	0.6747	0.4060	0.6372
No log	96.0	480	0.4063	0.6747	0.4063	0.6374
No log	96.4	482	0.4067	0.6747	0.4067	0.6378
No log	96.8	484	0.4069	0.6747	0.4069	0.6379
No log	97.2	486	0.4072	0.6747	0.4072	0.6381
No log	97.6	488	0.4074	0.6747	0.4074	0.6383
No log	98.0	490	0.4075	0.6747	0.4075	0.6384
No log	98.4	492	0.4076	0.6747	0.4076	0.6384
No log	98.8	494	0.4077	0.6747	0.4077	0.6385
No log	99.2	496	0.4077	0.6747	0.4077	0.6385
No log	99.6	498	0.4078	0.6747	0.4078	0.6386
0.1888	100.0	500	0.4078	0.6747	0.4078	0.6386

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1